Q-learning与蚁群算法代码

# -*- coding: utf-8 -*- import random import copy import time import sys import math import tkinter #//GUI模块 import threading from functools import reduce # 参数 ''' ALPHA:信息启发因子，值越大，则蚂蚁选择之前走过的路径可能性就越大 ，值越小，则蚁群搜索范围就会减少，容易陷入局部最优 BETA:Beta值越大，蚁群越就容易选择局部较短路径，这时算法收敛速度会 加快，但是随机性不高，容易得到局部的相对最优 ''' (ALPHA, BETA, RHO, Q) = (1.0,2.0,0.5,100.0) # 城市数，蚁群 (city_num, ant_num) = (50,50) distance_x = [ 178,272,176,171,650,499,267,703,408,437,491,74,532, 416,626,42,271,359,163,508,229,576,147,560,35,714, 757,517,64,314,675,690,391,628,87,240,705,699,258, 428,614,36,360,482,666,597,209,201,492,294] distance_y = [ 170,395,198,151,242,556,57,401,305,421,267,105,525, 381,244,330,395,169,141,380,153,442,528,329,232,48, 498,265,343,120,165,50,433,63,491,275,348,222,288, 490,213,524,244,114,104,552,70,425,227,331] #城市距离和信息素 distance_graph = [ [0.0 for col in range(city_num)] for raw in range(city_num)] pheromone_graph = [ [1.0 for col in range(city_num)] for raw in range(city_num)]#信息素矩阵 #----------- 蚂蚁 ----------- class Ant(object): # 初始化 def __init__(self,ID): self.ID = ID # ID self.__clean_data() # 随机初始化出生点 # 初始数据 def __clean_data(self): self.path = [] # 当前蚂蚁的路径 self.total_distance = 0.0 # 当前路径的总距离 self.move_count = 0 # 移动次数 self.current_city = -1 # 当前停留的城市 self.open_table_city = [True for i in range(city_num)] # 探索城市的状态 city_index = random.randint(0,city_num-1) # 随机初始出生点 self.current_city = city_index self.path.append(city_index) self.open_table_city[city_index] = False self.move_count = 1 # 选择下一个城市 def __choice_next_city(self): next_city = -1 select_citys_prob = [0.0 for i in range(city_num)] #存储去下个城市的概率 total_prob = 0.0 # 获取去下一个城市的概率 for i in range(city_num): if self.open_table_city[i]: try : # 计算概率：与信息素浓度成正比，与距离成反比 select_citys_prob[i] = pow(pheromone_graph[self.current_city][i], ALPHA) * pow((1.0/distance_graph[self.current_city][i]), BETA) total_prob += select_citys_prob[i] except ZeroDivisionError as e: print ('Ant ID: {ID}, current city: {current}, target city: {target}'.format(ID = self.ID, current = self.current_city, target = i)) sys.exit(1) # 轮盘选择城市 if total_prob > 0.0: # 产生一个随机概率,0.0-total_prob temp_prob = random.uniform(0.0, total_prob) for i in range(city_num): if self.open_table_city[i]: # 轮次相减 temp_prob -= select_citys_prob[i] if temp_prob < 0.0: next_city = i break # 未从概率产生，顺序选择一个未访问城市 # if next_city == -1: # for i in range(city_num): # if self.open_table_city[i]: # next_city = i # break if (next_city == -1): next_city = random.randint(0, city_num - 1) while ((self.open_table_city[next_city]) == False): # if==False,说明已经遍历过了 next_city = random.randint(0, city_num - 1) # 返回下一个城市序号 return next_city # 计算路径总距离 def __cal_total_distance(self): temp_distance = 0.0 for i in range(1, city_num): start, end = self.path[i], self.path[i-1] temp_distance += distance_graph[start][end] # 回路 end = self.path[0] temp_distance += distance_graph[start][end] self.total_distance = temp_distance # 移动操作 def __move(self, next_city): self.path.append(next_city) self.open_table_city[next_city] = False self.total_distance += distance_graph[self.current_city][next_city] self.current_city = next_city self.move_count += 1 # 搜索路径 def search_path(self): # 初始化数据 self.__clean_data() # 搜素路径，遍历完所有城市为止 while self.move_count < city_num: # 移动到下一个城市 next_city = self.__choice_next_city() self.__move(next_city) # 计算路径总长度 self.__cal_total_distance() #----------- TSP问题 ----------- class TSP(object): def __init__(self, root, width = 800, height = 600, n = city_num): # 创建画布 self.root = root self.width = width self.height = height # 城市数目初始化为city_num self.n = n # tkinter.Canvas self.canvas = tkinter.Canvas( root, width = self.width, height = self.height, bg = "#EBEBEB", # 背景白色 xscrollincrement = 1, yscrollincrement = 1 ) self.canvas.pack(expand = tkinter.YES, fill = tkinter.BOTH) self.title("TSP蚁群算法(n:初始化 e:开始搜索 s:停止搜索 q:退出程序)") self.__r = 5 self.__lock = threading.RLock() # 线程锁 self.__bindEvents() self.new() # 计算城市之间的距离 for i in range(city_num): for j in range(city_num): temp_distance = pow((distance_x[i] - distance_x[j]), 2) + pow((distance_y[i] - distance_y[j]), 2) temp_distance = pow(temp_distance, 0.5) distance_graph[i][j] =float(int(temp_distance + 0.5)) # 按键响应程序 def __bindEvents(self): self.root.bind("q", self.quite) # 退出程序 self.root.bind("n", self.new) # 初始化 self.root.bind("e", self.search_path) # 开始搜索 self.root.bind("s", self.stop) # 停止搜索 # 更改标题 def title(self, s): self.root.title(s) # 初始化 def new(self, evt = None): # 停止线程 self.__lock.acquire() self.__running = False self.__lock.release() self.clear() # 清除信息 self.nodes = [] # 节点坐标 self.nodes2 = [] # 节点对象 # 初始化城市节点 for i in range(len(distance_x)): # 在画布上随机初始坐标 x = distance_x[i] y = distance_y[i] self.nodes.append((x, y)) # 生成节点椭圆，半径为self.__r node = self.canvas.create_oval(x - self.__r, y - self.__r, x + self.__r, y + self.__r, fill = "#ff0000", # 填充红色 outline = "#000000", # 轮廓白色 tags = "node", ) self.nodes2.append(node) # 显示坐标 self.canvas.create_text(x,y-10, # 使用create_text方法在坐�